Language models suffer from adversarial vulnerability, where imperceptible perturbations in inputs can mislead model predictions. Existing adversarial training methods enhance model robustness by augmenting training data with worst-case adversarial perturbations for each input. However, these approaches overlook the intrinsic causal relationships within data. We construct causal graphs to model the behavior of encoder-based language models under adversarial inputs, suggesting that adversarial vulnerability is often associated with the model’s overfitting to spurious correlations. Within the adversarial training framework, we formulate expressions for Total Effect (TE) and Natural Direct Effect (NDE), and propose a causal regularization objective based on TE-NDE alignment. Experiments on five benchmark datasets show that this causal adversarial training framework improves adversarial robustness across different settings. We further evaluate the model behavior in a controlled sentiment analysis setting, where the quantitative results provide additional evidence for the effectiveness of our method.
This paper proposes a novel LVLM attack method, called BadPhase with further backdoor designs, to implant adversarial phase as triggers into any image inputs via data poisoning so as to control the LVLMs’ predictions and finds that LVLMs are sensitive to the phase-aware image structure.
Dai-Zong Liu, Junhao Dong, Xiang Fang et al.· Proceedings of the Thirty-Fi...· 0 citations
A collaborative adversarial fine-tuning framework that maintains multiple experts during training, enables knowledge exchange through embedding-space harmonization, and consolidates the learned knowledge into a single unified robust model.
Nguyen Duc Thai, Junhao Dong, Sua Qi Rong et al.· arXiv.org· 0 citations
Adversarial training (AT) is a widely adopted defense against adversarial attacks, but its multi-step optimization process for generating adversarial examples leads to substantial computational overhead. To mitigate this, various single-step adversarial training methods have been proposed. However, these models often s...
Lifeng Huang, Yuquan Lin, Chen Wan et al.· IEEE Transactions on Informa...· 0 citations
This survey provides a comprehensive analysis of adversarial prompting strategies, ranging from input manipulation techniques to semantic and structural distortions, and explores defense strategies across preprocessing, model-level, postprocessing, and hybrid strategies, highlighting recent advances and their limitatio...
A. Nasution, Ahmet Emre Ergün, Aytu˘g Onan et al.· IEEE Access· 0 citations
Evidential Adversarial Training (EV-AT), which models uncertainty through a Dirichlet distribution and combines an evidence-based loss promoting clean accuracy and reliable uncertainty with a robust evidence-alignment loss matching clean and adversarial predictions in log Dirichlet-parameter space, is proposed.
Nicolas Sournac, Ahmed Baha Ben Jmaa, B. Braeckeveldt· 0 citations
This work proposes a white-box spectral-subspace-guided attack (SSGRA) that aligns intermediate representations with the subspace spanned by the bottom right singular vectors, offering a spectral interpretation of adversarial vulnerability in VLMs, providing insights for improving their robustness.
Chethan Krishnamurthy Ramanaik, Tobias Callies, Michael Hecht et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
